character_set 1.2.0 → 1.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitattributes +3 -0
- data/.travis.yml +1 -0
- data/BENCHMARK.md +51 -15
- data/CHANGELOG.md +20 -0
- data/README.md +24 -8
- data/Rakefile +20 -18
- data/benchmarks/count_in.rb +13 -0
- data/benchmarks/delete_in.rb +1 -1
- data/benchmarks/scan.rb +13 -0
- data/benchmarks/shared.rb +1 -0
- data/benchmarks/z_add.rb +12 -0
- data/benchmarks/z_delete.rb +12 -0
- data/benchmarks/z_merge.rb +15 -0
- data/benchmarks/z_minmax.rb +12 -0
- data/bin/console +2 -0
- data/character_set.gemspec +2 -0
- data/ext/character_set/character_set.c +963 -413
- data/ext/character_set/unicode_casefold_table.h.tmpl +11 -0
- data/lib/character_set/core_ext/string_ext.rb +2 -0
- data/lib/character_set/expression_converter.rb +21 -24
- data/lib/character_set/predefined_sets.rb +25 -260
- data/lib/character_set/predefined_sets/any.cps +1 -0
- data/lib/character_set/predefined_sets/ascii.cps +1 -0
- data/lib/character_set/predefined_sets/ascii_alnum.cps +3 -0
- data/lib/character_set/predefined_sets/ascii_letter.cps +2 -0
- data/lib/character_set/predefined_sets/assigned.cps +666 -0
- data/lib/character_set/predefined_sets/bmp.cps +2 -0
- data/lib/character_set/predefined_sets/crypt.cps +2 -0
- data/lib/character_set/predefined_sets/emoji.cps +151 -0
- data/lib/character_set/predefined_sets/newline.cps +3 -0
- data/lib/character_set/predefined_sets/surrogate.cps +1 -0
- data/lib/character_set/predefined_sets/unicode.cps +2 -0
- data/lib/character_set/predefined_sets/url_fragment.cps +8 -0
- data/lib/character_set/predefined_sets/url_host.cps +10 -0
- data/lib/character_set/predefined_sets/url_path.cps +7 -0
- data/lib/character_set/predefined_sets/url_query.cps +8 -0
- data/lib/character_set/predefined_sets/whitespace.cps +10 -0
- data/lib/character_set/ruby_fallback.rb +0 -2
- data/lib/character_set/ruby_fallback/character_set_methods.rb +52 -4
- data/lib/character_set/ruby_fallback/set_methods.rb +2 -2
- data/lib/character_set/shared_methods.rb +51 -40
- data/lib/character_set/version.rb +1 -1
- metadata +54 -3
- data/lib/character_set/ruby_fallback/plane_methods.rb +0 -27
    
        metadata
    CHANGED
    
    | @@ -1,14 +1,14 @@ | |
| 1 1 | 
             
            --- !ruby/object:Gem::Specification
         | 
| 2 2 | 
             
            name: character_set
         | 
| 3 3 | 
             
            version: !ruby/object:Gem::Version
         | 
| 4 | 
            -
              version: 1. | 
| 4 | 
            +
              version: 1.3.0
         | 
| 5 5 | 
             
            platform: ruby
         | 
| 6 6 | 
             
            authors:
         | 
| 7 7 | 
             
            - Janosch Müller
         | 
| 8 8 | 
             
            autorequire: 
         | 
| 9 9 | 
             
            bindir: bin
         | 
| 10 10 | 
             
            cert_chain: []
         | 
| 11 | 
            -
            date: 2019- | 
| 11 | 
            +
            date: 2019-05-26 00:00:00.000000000 Z
         | 
| 12 12 | 
             
            dependencies:
         | 
| 13 13 | 
             
            - !ruby/object:Gem::Dependency
         | 
| 14 14 | 
             
              name: benchmark-ips
         | 
| @@ -24,6 +24,34 @@ dependencies: | |
| 24 24 | 
             
                - - "~>"
         | 
| 25 25 | 
             
                  - !ruby/object:Gem::Version
         | 
| 26 26 | 
             
                    version: '2.7'
         | 
| 27 | 
            +
            - !ruby/object:Gem::Dependency
         | 
| 28 | 
            +
              name: codecov
         | 
| 29 | 
            +
              requirement: !ruby/object:Gem::Requirement
         | 
| 30 | 
            +
                requirements:
         | 
| 31 | 
            +
                - - "~>"
         | 
| 32 | 
            +
                  - !ruby/object:Gem::Version
         | 
| 33 | 
            +
                    version: '0.1'
         | 
| 34 | 
            +
              type: :development
         | 
| 35 | 
            +
              prerelease: false
         | 
| 36 | 
            +
              version_requirements: !ruby/object:Gem::Requirement
         | 
| 37 | 
            +
                requirements:
         | 
| 38 | 
            +
                - - "~>"
         | 
| 39 | 
            +
                  - !ruby/object:Gem::Version
         | 
| 40 | 
            +
                    version: '0.1'
         | 
| 41 | 
            +
            - !ruby/object:Gem::Dependency
         | 
| 42 | 
            +
              name: get_process_mem
         | 
| 43 | 
            +
              requirement: !ruby/object:Gem::Requirement
         | 
| 44 | 
            +
                requirements:
         | 
| 45 | 
            +
                - - "~>"
         | 
| 46 | 
            +
                  - !ruby/object:Gem::Version
         | 
| 47 | 
            +
                    version: 0.2.3
         | 
| 48 | 
            +
              type: :development
         | 
| 49 | 
            +
              prerelease: false
         | 
| 50 | 
            +
              version_requirements: !ruby/object:Gem::Requirement
         | 
| 51 | 
            +
                requirements:
         | 
| 52 | 
            +
                - - "~>"
         | 
| 53 | 
            +
                  - !ruby/object:Gem::Version
         | 
| 54 | 
            +
                    version: 0.2.3
         | 
| 27 55 | 
             
            - !ruby/object:Gem::Dependency
         | 
| 28 56 | 
             
              name: rake
         | 
| 29 57 | 
             
              requirement: !ruby/object:Gem::Requirement
         | 
| @@ -116,6 +144,7 @@ extensions: | |
| 116 144 | 
             
            - ext/character_set/extconf.rb
         | 
| 117 145 | 
             
            extra_rdoc_files: []
         | 
| 118 146 | 
             
            files:
         | 
| 147 | 
            +
            - ".gitattributes"
         | 
| 119 148 | 
             
            - ".gitignore"
         | 
| 120 149 | 
             
            - ".rspec"
         | 
| 121 150 | 
             
            - ".travis.yml"
         | 
| @@ -125,17 +154,24 @@ files: | |
| 125 154 | 
             
            - LICENSE.txt
         | 
| 126 155 | 
             
            - README.md
         | 
| 127 156 | 
             
            - Rakefile
         | 
| 157 | 
            +
            - benchmarks/count_in.rb
         | 
| 128 158 | 
             
            - benchmarks/cover.rb
         | 
| 129 159 | 
             
            - benchmarks/delete_in.rb
         | 
| 130 160 | 
             
            - benchmarks/keep_in.rb
         | 
| 161 | 
            +
            - benchmarks/scan.rb
         | 
| 131 162 | 
             
            - benchmarks/shared.rb
         | 
| 132 163 | 
             
            - benchmarks/used_by.rb
         | 
| 164 | 
            +
            - benchmarks/z_add.rb
         | 
| 165 | 
            +
            - benchmarks/z_delete.rb
         | 
| 166 | 
            +
            - benchmarks/z_merge.rb
         | 
| 167 | 
            +
            - benchmarks/z_minmax.rb
         | 
| 133 168 | 
             
            - bin/console
         | 
| 134 169 | 
             
            - bin/setup
         | 
| 135 170 | 
             
            - character_set.gemspec
         | 
| 136 171 | 
             
            - ext/character_set/character_set.c
         | 
| 137 172 | 
             
            - ext/character_set/extconf.rb
         | 
| 138 173 | 
             
            - ext/character_set/unicode_casefold_table.h
         | 
| 174 | 
            +
            - ext/character_set/unicode_casefold_table.h.tmpl
         | 
| 139 175 | 
             
            - lib/character_set.rb
         | 
| 140 176 | 
             
            - lib/character_set/character.rb
         | 
| 141 177 | 
             
            - lib/character_set/core_ext.rb
         | 
| @@ -144,10 +180,25 @@ files: | |
| 144 180 | 
             
            - lib/character_set/expression_converter.rb
         | 
| 145 181 | 
             
            - lib/character_set/parser.rb
         | 
| 146 182 | 
             
            - lib/character_set/predefined_sets.rb
         | 
| 183 | 
            +
            - lib/character_set/predefined_sets/any.cps
         | 
| 184 | 
            +
            - lib/character_set/predefined_sets/ascii.cps
         | 
| 185 | 
            +
            - lib/character_set/predefined_sets/ascii_alnum.cps
         | 
| 186 | 
            +
            - lib/character_set/predefined_sets/ascii_letter.cps
         | 
| 187 | 
            +
            - lib/character_set/predefined_sets/assigned.cps
         | 
| 188 | 
            +
            - lib/character_set/predefined_sets/bmp.cps
         | 
| 189 | 
            +
            - lib/character_set/predefined_sets/crypt.cps
         | 
| 190 | 
            +
            - lib/character_set/predefined_sets/emoji.cps
         | 
| 191 | 
            +
            - lib/character_set/predefined_sets/newline.cps
         | 
| 192 | 
            +
            - lib/character_set/predefined_sets/surrogate.cps
         | 
| 193 | 
            +
            - lib/character_set/predefined_sets/unicode.cps
         | 
| 194 | 
            +
            - lib/character_set/predefined_sets/url_fragment.cps
         | 
| 195 | 
            +
            - lib/character_set/predefined_sets/url_host.cps
         | 
| 196 | 
            +
            - lib/character_set/predefined_sets/url_path.cps
         | 
| 197 | 
            +
            - lib/character_set/predefined_sets/url_query.cps
         | 
| 198 | 
            +
            - lib/character_set/predefined_sets/whitespace.cps
         | 
| 147 199 | 
             
            - lib/character_set/pure.rb
         | 
| 148 200 | 
             
            - lib/character_set/ruby_fallback.rb
         | 
| 149 201 | 
             
            - lib/character_set/ruby_fallback/character_set_methods.rb
         | 
| 150 | 
            -
            - lib/character_set/ruby_fallback/plane_methods.rb
         | 
| 151 202 | 
             
            - lib/character_set/ruby_fallback/set_methods.rb
         | 
| 152 203 | 
             
            - lib/character_set/set_method_adapters.rb
         | 
| 153 204 | 
             
            - lib/character_set/shared_methods.rb
         | 
| @@ -1,27 +0,0 @@ | |
| 1 | 
            -
            class CharacterSet
         | 
| 2 | 
            -
              module RubyFallback
         | 
| 3 | 
            -
                module PlaneMethods
         | 
| 4 | 
            -
                  def bmp_part
         | 
| 5 | 
            -
                    dup.keep_if { |cp| cp < 0x10000 }
         | 
| 6 | 
            -
                  end
         | 
| 7 | 
            -
             | 
| 8 | 
            -
                  def astral_part
         | 
| 9 | 
            -
                    dup.keep_if { |cp| cp >= 0x10000 }
         | 
| 10 | 
            -
                  end
         | 
| 11 | 
            -
             | 
| 12 | 
            -
                  def planes
         | 
| 13 | 
            -
                    plane_set = {}
         | 
| 14 | 
            -
                    plane_size = 0x10000.to_f
         | 
| 15 | 
            -
                    each do |cp|
         | 
| 16 | 
            -
                      plane = (cp / plane_size).floor
         | 
| 17 | 
            -
                      plane_set[plane] = true
         | 
| 18 | 
            -
                    end
         | 
| 19 | 
            -
                    plane_set.keys
         | 
| 20 | 
            -
                  end
         | 
| 21 | 
            -
             | 
| 22 | 
            -
                  def member_in_plane?(num)
         | 
| 23 | 
            -
                    ((num * 0x10000)...((num + 1) * 0x10000)).any? { |cp| include?(cp) }
         | 
| 24 | 
            -
                  end
         | 
| 25 | 
            -
                end
         | 
| 26 | 
            -
              end
         | 
| 27 | 
            -
            end
         |